Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: merge slurm support #40

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

feat: merge slurm support #40

wants to merge 5 commits into from

Conversation

wdconinc
Copy link
Contributor

Briefly, what does this PR introduce?

This adds csv submission support for slurm clusters.

@wdconinc wdconinc requested a review from rahmans1 December 21, 2024 02:12
Copy link
Contributor Author

@wdconinc wdconinc left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FYI comments. Feel free to resolve without action.

for i in `condor_q --batch | grep ^${USER} | tail -n1 | awk '{print($NF)}' | cut -d. -f1` ; do
mkdir -p LOG/CONDOR/osg_$i/
# slurm
max_array_size=2000
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Site dependent. No general way to query this on slurm clusters. Assumed but can also grep from /etc/slurm/slurm.conf, which is typical location. Or fall back to default of 1000.

mkdir -p LOG/CONDOR/osg_$i/
# slurm
max_array_size=2000
while [ ${NUM_JOBS} -ge 0 ] ; do
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Most of our submissions need multiple jobs at max array size to get through.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unchanged.

Comment on lines +6 to +7
#SBATCH --cpus-per-task=1
#SBATCH --mem=3G
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing compared to osg_csv.submit: disk space 5G, since not supported on slurm (there is tmp dir space, but that's different apparently).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant